DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
Open accessThe DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.
Abstract
Unsupervised Deep Learning (DL) techniques have been widely used in various security-related anomaly detection applications, owing to the great promise of being able to detect unforeseen threats and superior performance provided by Deep Neural Networks (DNN). However, the lack of interpretability creates key barriers to the adoption of DL models in practice. Unfortunately, existing interpretation approaches are proposed for supervised learning models and/or non-security domains, which are unadaptable for unsupervised DL models and fail to satisfy special requirements in security domains.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Similarly, a recent systematic review [31] highlighted that research on XAI for cybersecurity shows that many XAI applications are crafted without a thorough understanding of their integration into analyst workflows.”
From HuntGPT: Integrating Machine Learning-Based Anomaly Detection and Explainable AI with Large Language Models (LLMs) (2026) · cites this paper as [31]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Moreover, security literature frequently fails to differentiate between diverse use cases or clearly separate the roles of model users and designers, which could potentially lead to diminished adoption.”
From HuntGPT: Integrating Machine Learning-Based Anomaly Detection and Explainable AI with Large Language Models (LLMs) (2026) · cites this paper as [31]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“This problem can be solved by gradient-based optimization approaches (we use Adam optimizer [28] in this study) since the objective function is fully differentiable.”
MethodPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 2×
“, PyTorch [40]) set the embedding layer to be indifferentiable.”
BackgroundDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“However, embeddings of inputs are derived by an indifferentiable look-up operation [34] in many cases.”
BackgroundA Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1×
“For example, SHAP interpretation [32] is adapted to (single) Autoencoder in [2], which cannot be applied to Kitsune (ensemble Autoencoders) or other DL models.”
Method"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 2×
“Secondly, most prior methods are designed for non-security domains such as computer vision [16, 44, 62, 65] to understand the mechanism of DNNs.”
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123 · cited 2×
“The training data is collected from the purely benign authentication graphs through DeepWalk [41], which is a NN-based GE method.”
MethodTowards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859 · cited 1×
“We eliminate the box constraint (5) through the idea of change-of-variables [8] with tanh function.”
MethodGraph Neural Networks: A Review of Methods and Applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2018) · arXiv · doi:10.48550/arxiv.1812.08434 · Cited by 6,880 · cited 1×
“Graph data structure is useful for modeling a set of objects (nodes) and their relationships (links) at the same time [64].”
BackgroundGraph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“The simple approach is to compute gradients of the output relative to the input based on the back propagation mechanism of DNNs [46].”
Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization
Sharafaldin, I., Habibi Lashkari, A., & Ghorbani, A. A. (2018) · Proceedings of the 4th International Conference on Information Systems Security and Privacy · doi:10.5220/0006639801080116 · Cited by 5,318 · cited 2×
“For fairness and simplicity, we select two well-labeled multi-class datasets, Kitsune dataset [35] and CIC-IDS2017 [43].”
InfluentialOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087 · cited 1×
“Several improvements have been studied to solve the problem [3, 44, 48, 50].”
BackgroundDeep Learning for Anomaly Detection: A Review
Pang, G., Shen, C., Cao, L., & Hengel, A. V. D. (2022) · ACM Computing Surveys · doi:10.1145/3439950 · Cited by 2,837
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761 · cited 8×
“Among them, DeepLIFT [44] outperforms others by defining a reference in the input space and computing the back propagate changes in neuron activation to compute the contribution of change between the reference and interpreted sample.”
InfluentialMethods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
International Conference on Machine Learning (ICML)-2005
津田, 宏. (2006) · 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence · Cited by 2,558
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning
Du, M., Li, F., Zheng, G., & Srikumar, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134015 · Cited by 1,835 · cited 17×
“For DeepLog , we use HDFS dataset [57] which is the same dataset evaluated in its work.”
InfluentialDeep Learning for Anomaly Detection: A Review
Pang, G., Shen, C., Cao, L., et al. (2020) · Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · doi:10.48550/arxiv.2007.02500 · Cited by 1,718
Investigating Ad Transparency Mechanisms in Social Media: A Case Study of Facebook's Explanations
Andreou, A., Venkatadri, G., Goga, O., Gummadi, K. P., Loiseau, P., & Mislove, A. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23191 · Cited by 1,477
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467 · cited 1×
“Several improvements have been studied to solve the problem [3, 44, 48, 50].”
BackgroundAnomaly Detection with Robust Deep Autoencoders
Zhou, C., & Paffenroth, R. C. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098052 · Cited by 1,436 · cited 1×
“This kind of learning approaches are achieved by generative DL models, such as Autoencoder [35, 56, 63] and Generative Adversarial Networks (GAN) [59].”
Explaining nonlinear classification decisions with deep taylor decomposition
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., & Müller, K.-R. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.008 · Cited by 1,357
Detecting large-scale system problems by mining console logs
Xu, W., Huang, L., Fox, A., Patterson, D., & Jordan, M. I. (2009) · Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles · doi:10.1145/1629575.1629587 · Cited by 1,332 · cited 2×
“For DeepLog , we use HDFS dataset [57] which is the same dataset evaluated in its work.”
Interpretable Explanations of Black Boxes by Meaningful Perturbation
Fong, R. C., & Vedaldi, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.371 · Cited by 1,097 · cited 21×
“In [7], a dedicated interpretation for Isolation Forest is developed which also cannot be applied to DNNs.”
InfluentialMusa, T. H. A., & Bouras, A. (2022) · Lecture Notes in Networks and Systems · doi:10.1007/978-981-16-2102-4_36 · Cited by 958
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375830 · Cited by 900 · cited 1×
“For another, existing interpretations have shown to be vulnerable to adversarial attacks [18, 47, 60] or even random noise [14, 54].”
BackgroundUnsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications
Xu, H., Feng, Y., Chen, J., Wang, Z., Qiao, H., Chen, W., Zhao, N., Li, Z., Bu, J., Li, Z., et al. (2018) · Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18 · doi:10.1145/3178876.3185996 · Cited by 808 · cited 2×
“This kind of learning approaches are achieved by generative DL models, such as Autoencoder [35, 56, 63] and Generative Adversarial Networks (GAN) [59].”
Self-citationAI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., & Vechev, M. (2018) · 2018 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2018.00058 · Cited by 799 · cited 1×
“Recently, several works have been proposed for improving the practicality of (unsupervised) DL-based security systems, such as improving the robustness of DL-based systems [17, 21], performing lifelong learning [11], detecting concept drift [58], learning from low-quality labeled data [30].”
Interpretation of Neural Networks Is Fragile
Ghorbani, A., Abid, A., & Zou, J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013681 · Cited by 765
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629 · cited 1×
“Although DL interpretability has been extensively studied [19, 37], we argue that existing interpretations are unadaptable for unsupervised DL-based security systems for the following two reasons.”
BackgroundUnderstanding Deep Networks via Extremal Perturbations and Smooth Masks
Fong, R., Patrick, M., & Vedaldi, A. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00304 · Cited by 538 · cited 21×
“In [7], a dedicated interpretation for Isolation Forest is developed which also cannot be applied to DNNs.”
InfluentialExplaining anomalies detected by autoencoders using Shapley Additive Explanations
Antwarg, L., Miller, R. M., Shapira, B., & Rokach, L. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115736 · Cited by 496
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
Zintgraf, L. M., Cohen, T. S., Adel, T., & Welling, M. (2017) · arXiv · doi:10.48550/arxiv.1702.04595 · Cited by 487
Adversarially Learned Anomaly Detection
Zenati, H., Romain, M., Foo, C.-S., Lecouat, B., & Chandrasekhar, V. (2018) · 2018 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2018.00088 · Cited by 397
UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats
Han, X., Pasquier, T., Bates, A., Mickens, J., & Seltzer, M. (2020) · Proceedings 2020 Network and Distributed System Security Symposium · doi:10.14722/ndss.2020.24046 · Cited by 349 · cited 1×
“Especially for advanced persistent threat (APT) detection, researchers have leveraged Graph Neural Networks (GNN) or Graph Embedding (GE) for unsupervised detection [6, 22].”
BackgroundLEMNA: Explaining Deep Learning based Security Applications
Guo, W., Mu, D., Xu, J., Su, P., Wang, G., & Xing, X. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243792 · Cited by 287 · cited 4×
“On the other hand, the white-box condition makes sense when the one seeking interpretations is the model owner.”
InfluentialBeyond Sparsity: Tree Regularization of Deep Models for Interpretability
Wu, M., Hughes, M., Parbhoo, S., Zazzi, M., Roth, V., & Doshi-Velez, F. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11501 · Cited by 213
Flow-based intrusion detection: Techniques and challenges
Umer, M. F., Sher, M., & Bi, Y. (2017) · Computers & Security · doi:10.1016/j.cose.2017.05.009 · Cited by 203
Han, D., Wang, Z., Zhong, Y., Chen, W., Yang, J., Lu, S., Shi, X., & Yin, X. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3087242 · Cited by 190 · cited 1×
“Recently, several works have been proposed for improving the practicality of (unsupervised) DL-based security systems, such as improving the robustness of DLbased systems [17, 21], performing lifelong learning [11], detecting concept drift [58], learning from low-quality labeled data [30].”
BackgroundSelf-citationHELAD: A novel network anomaly detection model based on heterogeneous ensemble learning
Zhong, Y., Chen, W., Wang, Z., Chen, Y., Wang, K., Li, Y., Yin, X., Shi, X., Yang, J., & Li, K. (2020) · Computer Networks · doi:10.1016/j.comnet.2019.107049 · Cited by 171
Self-citationCyber security data sources for dynamic network research
Kent, A. D. (2016) · Security Science and Technology · doi:10.1142/9781786340757_0002 · Cited by 163 · cited 1×
“For GLGV , we also use a dataset evaluated in its original work called LANL-CMSCSE[27], which collects tons of multi-source events of a real internal computer network in 58 consecutive days.”
From Clustering to Cluster Explanations via Neural Networks
Kauffmann, J., Esders, M., Ruff, L., Montavon, G., Samek, W., & Müller, K. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3185901 · Cited by 161
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S. K., & Lakkaraju, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02508 · Cited by 155 · cited 1×
“For another, existing interpretations have shown to be vulnerable to adversarial attacks [18, 47, 60] or even random noise [14, 54].”
BackgroundNguyen, A. M., Yosinski, J., & Clune, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.03616 · Cited by 152 · cited 1×
“Consequently, Some interpretations used to understand the operating mechanism of DNN are not applicable to security applications [13, 39, 62].”
BackgroundDetecting Lateral Movement in Enterprise Computer Networks with Unsupervised Graph {AI}
Bowman, B., Laprade, C. A., Ji, Y., & Huang, H. H. (2020) · Recent Advances in Intrusion Detection · Cited by 146
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection
Mirsky, Y., Doitshman, T., Elovici, Y., & Shabtai, A. (2018) · Proceedings 2018 Network and Distributed System Security Symposium · doi:10.14722/ndss.2018.23204 · Cited by 128
Toward Explainable Deep Neural Network Based Anomaly Detection
Amarasinghe, K., Kenney, K., & Manic, M. (2018) · 2018 11th International Conference on Human System Interaction (HSI) · doi:10.1109/hsi.2018.8430788 · Cited by 127 · cited 1×
“There are also works converting anomaly detection to supervised tasks and leverage existing supervised interpretations [1, 38].”
BackgroundEvaluating Explanation Methods for Deep Learning in Security
Warnecke, A., Arp, D., Wressnegger, C., & Rieck, K. (2020) · 2020 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp48549.2020.00018 · Cited by 127 · cited 5×
“For another, existing interpretations have shown to be vulnerable to adversarial attacks [18, 47, 60] or even random noise [14, 54].”
BackgroundResultInfluentialZeroWall: Detecting Zero-Day Web Attacks through Encoder-Decoder Recurrent Neural Networks
Tang, R., Yang, Z., Li, Z., Meng, W., Wang, H., Li, Q. L., Sun, Y., Pei, D., Tao, W., Xu, Y., et al. (2020) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom41043.2020.9155278 · Cited by 125 · cited 1×
“So far, unsupervised deep learning models have been applied in various security-related anomaly detection applications, such as network intrusion detection [35], system log anomaly detection [12], advanced persistent threat (APT) detection [6], domain generation algorithm (DGA) detection [45] and web attack detection…”
MethodInterpretable Deep Learning under FirePreprint
Zhang, X., Wang, N., Shen, H., Ji, S., Luo, X., & Wang, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00891 · Cited by 122 · cited 3×
“Gradient-based interpretations are vulnerable against adversarial attacks [18, 60] since attackers can also use the gradients for adversarial optimization.”
BackgroundTowards Explanation of DNN-based Prediction with Guided Feature Inversion
Du, M., Liu, N., Song, Q., & Hu, X. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220099 · Cited by 118 · cited 1×
“However, this is not the case for un-supervised DL models since they are not supposed to learn any [13, 39, 62].”
Lifelong Anomaly Detection Through Unlearning
Du, M., Chen, Z., Liu, C., Oak, R., & Song, D. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363226 · Cited by 118 · cited 7×
“If the anomaly is caused by 𝒙 ◦ , then we can simply replace 𝒙 ◦ with the following 𝒙 ∗ to turn the time-series into normal: Such 𝒙 ∗ can be obtained directly by observing the index of the maximum probability in the last layer (usually softmax) of the RNN/LSTM.”
InfluentialTowards explaining anomalies: A deep Taylor decomposition of one-class models
Kauffmann, J., Müller, K.-R., & Montavon, G. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107198 · Cited by 101
Deep Learning for Anomaly Detection
Wang, R., Nie, K., Wang, T., Yang, Y., & Long, B. (2020) · Proceedings of the 13th International Conference on Web Search and Data Mining · doi:10.1145/3336191.3371876 · Cited by 100
MacroBase: Prioritizing Attention in Fast Data
Bailis, P., Gan, E., Madden, S., Narayanan, D., Rong, K., & Suri, S. (2017) · Proceedings of the 2017 ACM International Conference on Management of Data · doi:10.1145/3035918.3035928 · Cited by 99
Interpreting Deep Learning-Based Networking Systems
Meng, Z., Wang, M., Bai, J., Xu, M., Mao, H., & Hu, H. (2020) · Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication · doi:10.1145/3387514.3405859 · Cited by 99 · cited 2×
“Why Not Existing Distillation Approaches? Knowledge distillation has been proposed to provide global interpretations by replacing the entire DL models with interpretable models [33, 55] (Note that they differ from approximation-based methods in §2.”
BackgroundMethodBeyond Sparsity: Tree Regularization of Deep Models for Interpretability
Wu, M., Hughes, M. C., Parbhoo, S., Zazzi, M., Röth, V., & Doshi‐Velez, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.06178 · Cited by 88 · cited 1×
“Why Not Existing Distillation Approaches? Knowledge distillation has been proposed to provide global interpretations by replacing the entire DL models with interpretable models [33, 55] (Note that they differ from approximation-based methods in §2.”
MethodCarletti, M., Masiero, C., Beghi, A., & Susto, G. A. (2019) · 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) · doi:10.1109/smc.2019.8913901 · Cited by 85 · cited 1×
“In [7], a dedicated interpretation for Isolation Forest is developed which also cannot be applied to DNNs.”
MethodInterpreting Deep Learning-Based Networking Systems
Meng, Z., Wang, M., Bai, J., Xu, M., Mao, H., & Hu, H. (2020) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 85
EXPLAIN-IT: Towards Explainable AI for Unsupervised Network Traffic Analysis
Morichetta, A., Casas, P., & Mellia, M. (2019) · Proceedings of the 3rd ACM CoNEXT Workshop on Big DAta, Machine Learning and Artificial Intelligence for Data Communication Networks · doi:10.1145/3359992.3366639 · Cited by 82 · cited 1×
“There are also works converting anomaly detection to supervised tasks and leverage existing supervised interpretations [1, 38].”
BackgroundExplaining Image Classifiers by Counterfactual Generation
Chang, C., Creager, E., Goldenberg, A., & Duvenaud, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.08024 · Cited by 79 · cited 1×
“Impactful input features with small perturbations are more likely to induce major change in the outputs of DNNs [10, 15, 16, 65].”
Barbado, A., Corcho, Ó., & Benjamins, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116100 · Cited by 77 · cited 1×
“First, some studies develop global interpretation through model distillation [49] and rule extraction [5] as well as interpretation for clustering models [25], which are beyond the scope of this study.”
BackgroundExplaining Anomalies Detected by Autoencoders Using SHAP
Antwarg, L., Miller, R. M., Shapira, B., & Rokach, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02407 · Cited by 76 · cited 1×
“For example, SHAP interpretation [32] is adapted to (single) Autoencoder in [2], which cannot be applied to Kitsune (ensemble Autoencoders) or other DL models.”
MethodContextual Outlier Interpretation
Liu, N., Shin, D., & Hu, X. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/341 · Cited by 74
UNICORN:Runtime Provenance-Based Detector for Advanced Persistent Threats
Han, X., Pasquier, T., Bates, A., Mickens, J. W., & Seltzer, M. (2020) · Explore Bristol Research · Cited by 69
Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysis
Fan, M., Wei, W., Xie, X., Liu, Y., Guan, X., & Liu, T. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3021924 · Cited by 65
An approximate L0 norm minimization algorithm for compressed sensing
Hyder, M. M., & Mahata, K. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4960346 · Cited by 64 · cited 1×
“Firstly, 𝐿 0 -norm minimization problem is proven to be NP-hard [23].”
FARE: Enabling Fine-grained Attack Categorization under Low-quality Labeled Data
Liang, J., Guo, W., Luo, T., Honavar, V., Wang, G., & Xing, X. (2021) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24403 · Cited by 44 · cited 1×
“Recently, several works have been proposed for improving the practicality of (unsupervised) DL-based security systems, such as improving the robustness of DL-based systems [17, 21], performing lifelong learning [11], detecting concept drift [58], learning from low-quality labeled data [30].”
EXAD: A System for Explainable Anomaly Detection on Big Data Traces
Song, F., Diao, Y., Read, J., Stiegler, A., & Bifet, A. (2018) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2018.00204 · Cited by 31 · cited 1×
“First, some studies develop global interpretation through model distillation [49] and rule extraction [5] as well as interpretation for clustering models [25], which are beyond the scope of this study.”
BackgroundHelix: DGA Domain Embeddings for Tracking and Exploring Botnets
Sidi, L., Mirsky, Y., Nadler, A., Elovici, Y., & Shabtai, A. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3416022 · Cited by 15 · cited 1×
“…learning models have been applied in various security-related anomaly detection applications, such as network intrusion detection [35], system log anomaly detection [12], advanced persistent threat (APT) detection [6], domain generation algorithm (DGA) detection [45] and web attack detection [51].”
Explainable Anomaly Detection via Feature-Based Localization
Kitamura, S., & Nonaka, Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30493-5_41 · Cited by 12 · cited 1×
“An interpretation method for convolutional models and image analysis is proposed in [29] by visualizing abnormal region, which is unadaptable for other DL models in security domains.”
MethodMacroBase: Prioritizing Attention in Fast DataPreprint
Bailis, P. D., Gan, E., Madden, S. R., Narayanan, D., Rong, K., & Suri, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.00567 · Cited by 9
AnomalyBench: An Open Benchmark for Explainable Anomaly Detection.Preprint
Jacob, V., Song, F., Stiegler, A., Diao, Y., & Tatbul, N. (2020) · arXiv (Cornell University) · Cited by 7
Research works printed but not linked: 2
- Alexander D. Kent. 2015. Cybersecurity Data Sources for Dynamic Network Research. In Dynamic Networks in Cybersecurity. Imperial College Press.
- Limin Yang, Wenbo Guo, Qingying Hao, Arridhana Ciptadi, Ali Ahmadzadeh, Xinyu Xing, and Gang Wang. 2021. CADE: Detecting and Explaining Concept Drift Samples for Security Applications. In 30th USENIX Security Symposium (USENIX Security).
Cited by
Wang, Y., Sun, T., Li, S., Yuan, X., Ni, W., Hossain, E., & Vincent Poor, H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3319492 · Cited by 161
Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenance
Cheng, Z., Lv, Q., Liang, J., Wang, Y., Sun, D., Pasquier, T., & Han, X. (2024) · 2024 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp54263.2024.00005 · Cited by 132
“This is because attack reconstruction (1) establishes trust on the decisions, (2) facilitates the necessary human-in-the-loop component in understanding system anomalies, and (3) expedites the process of identifying and reducing FPs (§5.2) [66].”
BackgroundInfluentialArreche, O., Guntur, T. R., & Abdallah, M. (2024) · Applied Sciences · doi:10.3390/app14104170 · Cited by 224
E-XAI: Evaluating Black-Box Explainable AI Frameworks for Network Intrusion Detection
Arreche, O., Guntur, T. R., Roberts, J. W., & Abdallah, M. (2024) · IEEE Access · doi:10.1109/access.2024.3365140 · Cited by 217
“Similarly, the work [31] contributes a new framework called DeepAID, aiming to address the limitations of unsupervised DL-based anomaly detection systems.”
MethodFlash: A Comprehensive Approach to Intrusion Detection via Provenance Graph Representation Learning
Rehman, M. U., Ahmadi, H., & Hassan, W. U. (2024) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp54263.2024.00139 · Cited by 262
“DeepAid [29] uses deep neural networks to detect anomalies in network traffic.”
Background
Metadata
- Authors
- Han, D., Wang, Z., Chen, W., Zhong, Y., Wang, S., Zhang, H., Yang, J., Shi, X., & Yin, X.
- Affiliations
- Tsinghua University (CN)
- ORCID
- Venue
- Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2021-11-12
- Pages
- 3197-3217
- ISSN
- 1543-7221 (ISSN-L)
- OpenAlex
- W3200583622
- Cited by
- 121
- References
- 76
- Citations by year
- 2026: 9 · 2025: 38 · 2024: 42 · 2023: 25 · 2022: 7
- FWCI
- 8.53
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM SIGSAC Conference on Computer and Communications Security (CCS) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2018YFB1800200)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Keywords
- anomaly detection, interpretability, unsupervised deep learning, deep neural network, security applications, explainable AI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.